@inproceedings{wu-etal-2026-atlas,
    title = "{ATLAS}: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning",
    author = "Wu, Jinyang  and
      Zhai, Guocheng  and
      Jin, Ruihan  and
      Yuan, Jiahao  and
      Shen, Yuhao  and
      Zhang, Shuai  and
      Wen, Zhengqi  and
      Tao, Jianhua",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.867/",
    pages = "17503--17535",
    ISBN = "979-8-89176-395-1",
    abstract = "The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a high-dimensional optimization challenge. Existing approaches often rely on a single model or fixed tool-calling logic, failing to exploit the performance variations across heterogeneous model-tool pairs. In this paper, we present **ATLAS** (**A**daptive **T**ool-**L**LM **A**lignment and **S**ynergistic Invocation), a dual-path framework for dynamic tool usage in cross-domain complex reasoning. **ATLAS** operates via a dual-path approach: (1) **training-free cluster-based routing** that exploits empirical priors for domain-specific alignment, and (2) **RL-based multi-step routing** that explores autonomous trajectories for out-of-distribution generalization. Extensive experiments across 15 benchmarks demonstrate that our method outperforms closed-source models like GPT-4o as well as existing routing methods on both in-distribution (+10.1{\%}) and out-of-distribution (+13.1{\%}) tasks. Furthermore, our framework shows significant gains in visual reasoning by orchestrating specialized multi-modal tools."
}